© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50548
    Prev
    Next
    INDEX
    Explanations

    without using arithmeticrecursion without arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ش
    0.47
    j
    0.47
     prominence
    0.46
    l
    0.45
     turns
    0.43
    celebr
    0.43
    p
    0.42
     hallmarks
    0.42
     lovingly
    0.41
    b
    0.40
    POSITIVE LOGITS
     ذہنی
    0.48
     หัด
    0.47
     систем
    0.46
     estudiando
    0.44
     girdi
    0.44
     vazio
    0.43
    的研究
    0.43
    📄
    0.42
     dhinak
    0.42
     penyakit
    0.42
    Activations Density 0.002%

    No Known Activations